Jove
Visualize
Contact Us

Related Concept Videos

Cancer Survival Analysis01:21

Cancer Survival Analysis

863
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
863

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Neonatal and maternal outcomes following transfer of vitrified embryos compared with slow-frozen and fresh embryos: a retrospective study in singletons.

BMC pregnancy and childbirth·2026
Same author

Mechanism-guided biomaterial strategies for intervertebral disc degeneration: Pathological heterogeneity, functional classification, and translational perspectives.

Journal of tissue engineering·2026
Same author

Prediction of Ki-67 expression in hepatocellular carcinoma: a dual-center study based on T2-weighted imaging habitat analysis.

Radiology and oncology·2026
Same author

Enhancing gynecological examination training for international medical students: a comparative study of peer role-play and peer assessment.

BMC medical education·2026
Same author

Targeted knockdown of Piezo1 in synovial macrophages attenuates osteoarthritis development.

Journal of orthopaedic translation·2026
Same author

Electroacupuncture alleviates cognitive impairment in mice with vascular dementia by regulating the cholinergic vasodilation system.

Frontiers in aging neuroscience·2026
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 4, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K

CT-Based 2.5D Deep Learning-Multi-Instance Learning for Predicting Early Recurrence of Hepatocellular Carcinoma and

Yongyi Cen1,2, Haiyang Nong1,2, Dehui Du3

  • 1Department of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities, Baise, Guangxi Zhuang Autonomous Region, 533000, People's Republic of China.

Journal of Hepatocellular Carcinoma
|September 23, 2025
PubMed
Summary

The 2.5D deep learning-multi-instance learning (DL-MIL) model accurately predicts early recurrence (ER) in hepatocellular carcinoma (HCC). Its features correlate with tumor invasiveness and proliferation, offering significant clinical value.

Keywords:
CTdeep learningearly recurrencehepatocellular carcinomamulti-instance learning

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.4K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

493

Related Experiment Videos

Last Updated: May 4, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.6K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.4K
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
07:13

Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model

Published on: April 18, 2025

493

Area of Science:

  • Hepatocellular Carcinoma Research
  • Medical Imaging Analysis
  • Artificial Intelligence in Oncology

Background:

  • Hepatocellular carcinoma (HCC) recurrence after treatment poses a significant clinical challenge.
  • Accurate prediction of early recurrence (ER) is crucial for timely intervention and improved patient outcomes.
  • Current predictive models require enhancement for greater accuracy and biological insight.

Purpose of the Study:

  • To evaluate the predictive performance of a 2.5D deep learning-multi-instance learning (DL-MIL) model for ER in HCC using CT arterial phase images.
  • To explore the biological significance and clinical relevance of MIL features identified by the DL-MIL model.
  • To compare the efficacy of the 2.5D DL-MIL model against traditional Radiomics and Clinical models.

Main Methods:

  • Retrospective analysis of CT arterial phase images and clinical data from 191 HCC patients (79 ER, 112 non-ER).
  • Development and comparison of 2.5D DL-MIL, Radiomics, and Clinical predictive models.
  • Utilized SHAP analysis to interpret MIL feature contributions and correlation analysis for biological significance (MVI, Ki-67, grading).

Main Results:

  • The 2.5D DL-MIL model achieved a superior AUC of 0.840 in the validation set, outperforming Radiomics (0.678) and Clinical (0.598) models.
  • SHAP analysis identified key bag-of-words features (BoW_02, BoW_09) as significant contributors to the DL-MIL model's predictive power.
  • MIL features (BoW_01, BoW_02, BoW_09, BoW_1) showed significant correlations with microvascular invasion (MVI) grade and Ki-67 expression.

Conclusions:

  • The 2.5D DL-MIL model demonstrates significant potential for predicting ER in HCC.
  • The identified MIL features provide biological insights into tumor invasiveness and proliferative activity, enhancing model interpretability.
  • The model offers superior clinical utility compared to existing Radiomics and Clinical approaches.